Merge branch 'main' of github.com:666ghj/Weibo_PublicOpinion_AnalysisSystem

.gitignore

@@ -1 +1,2 @@
 .conda
+*__pycache__/

.idea/.name

@@ -0,0 +1 @@
+app.py

.idea/Weibo_PublicOpinion_AnalysisSystem.iml

@@ -5,7 +5,7 @@
   </component>
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="inheritedJdk" />
+    <orderEntry type="jdk" jdkName="Python 3.9" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
   <component name="TemplatesService">

.idea/misc.xml

@@ -3,5 +3,8 @@
   <component name="Black">
     <option name="sdkName" value="Python 3.12 (Desktop)" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (Desktop)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
+  <component name="PyCharmProfessionalAdvertiser">
+    <option name="shown" value="true" />
+  </component>
 </project>

model/cipingTotal.csv

@@ -1,100 +0,0 @@
-('哈哈', 1236)
-('哈哈哈', 537)
-('哈哈哈哈', 157)
-('真的', 154)
-('期待', 89)
-('喜欢', 89)
-('doge', 88)
-('宝宝', 87)
-('可爱', 79)
-('第一', 73)
-('演唱', 71)
-('亲亲', 71)
-('苦涩', 70)
-('啊啊啊', 68)
-('抱抱', 64)
-('cry', 64)
-('宝贝', 62)
-('姐姐', 51)
-('花花', 50)
-('送花', 48)
-('开心', 47)
-('加油', 47)
-('老师', 46)
-('call', 45)
-('特别', 42)
-('一个', 42)
-('抓狂', 40)
-('嘻嘻', 39)
-('心心', 38)
-('悲伤', 38)
-('世界', 37)
-('感觉', 35)
-('孩子', 35)
-('朋友', 34)
-('鲜花', 34)
-('开学', 34)
-('好好', 34)
-('演唱会', 33)
-('感谢', 32)
-('憧憬', 31)
-('学季', 31)
-('快乐', 30)
-('漂亮', 30)
-('中国', 30)
-('音乐', 29)
-('电影', 28)
-('莲花', 28)
-('骄阳', 28)
-('视频', 27)
-('老公', 27)
-('老婆', 27)
-('值得', 26)
-('好看', 26)
-('消失', 26)
-('希望', 25)
-('呜呜', 25)
-('少年', 25)
-('东西', 25)
-('实力', 24)
-('评论', 24)
-('舞台', 24)
-('生活', 24)
-('单身', 24)
-('努力', 23)
-('唯一', 23)
-('幸福', 23)
-('时间', 23)
-('超级', 23)
-('辈子', 22)
-('童年', 22)
-('时代', 22)
-('可怜', 21)
-('不见', 21)
-('工作', 21)
-('有人', 21)
-('终于', 21)
-('粉丝', 21)
-('国家', 21)
-('callcallcall', 21)
-('永远', 21)
-('太阳', 20)
-('直播', 20)
-('小时', 20)
-('星期', 20)
-('安全', 20)
-('代言', 19)
-('支持', 19)
-('彩虹', 19)
-('妈妈', 18)
-('华为', 18)
-('优秀', 18)
-('好像', 18)
-('越来', 18)
-('大人', 18)
-('父母', 18)
-('害怕', 18)
-('安哥', 18)
-('加班', 18)
-('一点', 18)
-('一场', 17)

model/cutComments.py

@@ -1,29 +0,0 @@
-from utils.getPublicData import getAllCommentsData
-import jieba
-targetTxt = 'cutComments.txt'
-
-def stopWordList():
-    stopWords = [line.strip() for line in open('./stopWords.txt',encoding='utf8').readlines()]
-    return stopWords
-
-def seg_depart(sentence):
-    sentence_depart = jieba.cut(" ".join([x[4] for x in sentence]).strip())
-    stopWords = stopWordList()
-    outStr = ''
-    for word in sentence_depart:
-        if word not in stopWords:
-            if word != '\t':
-                outStr += word
-    return outStr
-
-def writer_comments_cuts():
-    with open(targetTxt,'a+',encoding='utf-8') as targetFile:
-        seg = jieba.cut(seg_depart(getAllCommentsData()),cut_all=True)
-        output = ' '.join(seg)
-        targetFile.write(output)
-        targetFile.write('\n')
-        print('写入成功')
-
-
-if __name__ == '__main__':
-    writer_comments_cuts()

utils/cipingTotal.csv

@@ -0,0 +1,100 @@
+('宝宝', 142)
+('祝福', 80)
+('期待', 77)
+('喜欢', 73)
+('恭喜', 73)
+('接接', 71)
+('真的', 62)
+('第一', 50)
+('快乐', 49)
+('祖国', 34)
+('舞台', 33)
+('朋友', 33)
+('老公', 32)
+('毕业', 32)
+('谢谢', 28)
+('好好', 27)
+('开心', 27)
+('维维', 26)
+('加油', 25)
+('哥哥', 25)
+('视频', 24)
+('世界', 24)
+('永远', 23)
+('好听', 23)
+('香港', 23)
+('希望', 22)
+('孩子', 21)
+('七月', 20)
+('朋友圈', 19)
+('敦豪', 19)
+('生活', 18)
+('宝贝', 18)
+('合作', 18)
+('day', 18)
+('好看', 18)
+('可爱', 17)
+('老师', 17)
+('涂山', 17)
+('致敬', 17)
+('中国', 17)
+('感觉', 16)
+('生日', 16)
+('幸福', 16)
+('记得', 16)
+('追风', 16)
+('蟑螂', 16)
+('终于', 16)
+('评论', 15)
+('厉害', 15)
+('下次', 15)
+('一点', 15)
+('双人', 15)
+('见面', 15)
+('关注', 15)
+('实至名归', 14)
+('妹妹', 14)
+('打开', 14)
+('热巴', 14)
+('流水', 14)
+('任何', 13)
+('手机', 13)
+('活动', 13)
+('呜呜', 13)
+('何人', 13)
+('电影', 13)
+('你好', 13)
+('任何人', 13)
+('北京', 13)
+('粉丝', 13)
+('顺利', 13)
+('太棒', 12)
+('支持', 12)
+('奥运', 12)
+('人气', 12)
+('by', 12)
+('漂亮', 12)
+('大哥', 12)
+('生日快乐', 12)
+('老婆', 12)
+('精彩', 12)
+('工作', 12)
+('照顾', 12)
+('迢迢', 12)
+('时间', 12)
+('初心', 12)
+('更好', 11)
+('早安', 11)
+('未来', 11)
+('美好', 11)
+('造型', 11)
+('晚上', 11)
+('满满', 11)
+('火炬', 10)
+('明天', 10)
+('魅力', 10)
+('实况', 10)
+('爷爷', 10)
+('骄傲', 10)
+('有没有', 10)
+('火炬手', 10)

utils/cipingTotal.py

@@ -4,7 +4,7 @@ import re
 def main():
     reader = open('./cutComments.txt','r',encoding='utf8')
     strs = reader.read()
-    result = open('./cipingTotal.csv','w',encoding='utf8')
+    result = open('cipingTotal.csv', 'w', encoding='utf8')
 
     # 分词，去重，列表
     word_list = jieba.cut(strs,cut_all=True)

utils/cutComments.py

@@ -0,0 +1,44 @@
+from utils.getPublicData import getAllCommentsData
+import jieba
+import re
+targetTxt = 'cutComments.txt'
+
+def stopWordList():
+    stopWords = [line.strip() for line in open('./stopWords.txt',encoding='utf8').readlines()]
+    return stopWords
+
+def seg_depart(sentence):
+    sentence_depart = jieba.cut(" ".join([clean(x[4]) for x in sentence]).strip())
+    stopWords = stopWordList()
+    outStr = ''
+    for word in sentence_depart:
+        if word not in stopWords:
+            if word != '\t':
+                outStr += word
+    return outStr
+
+def writer_comments_cuts():
+    with open(targetTxt,'w+',encoding='utf-8') as targetFile:
+        seg = jieba.cut(seg_depart(getAllCommentsData()))
+        output = ' '.join(seg)
+        targetFile.write(output)
+        targetFile.write('\n')
+        print('写入成功')
+
+def clean(text):
+    text = re.sub(r"(回复)?(//)?\s*@\S*?\s*(:| |$)", " ", text)  # 去除正文中的@和回复/转发中的用户名
+    text = re.sub(r"\[\S+\]", "", text)  # 去除表情符号
+    # text = re.sub(r"#\S+#", "", text)      # 保留话题内容
+    # 去除emoji表情的正则表达式
+    text = re.compile(u'[\U00010000-\U0010ffff]').sub('',text)
+    URL_REGEX = re.compile(
+        r'(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'".,<>?«»“”‘’]))',
+        re.IGNORECASE)
+    text = re.sub(URL_REGEX, "", text)  # 去除网址
+    text = text.replace("转发微博", "")  # 去除无意义的词语
+    text = re.sub(r"\s+", " ", text)  # 合并正文中过多的空格
+    return text.strip()
+
+if __name__ == '__main__':
+    writer_comments_cuts()
+    # print(clean("想到一次我也看到了这样的，我把我的外套（喷了淡茉莉香水的）递过去了，我当时觉得她可能是因为地铁空调有点冷一直环抱着，我借给她说冷的话可以披一下，我坐到终点站的，然后她说不用了，我好尴尬哇"))

utils/errorResponse.py

@@ -1,4 +1,3 @@
 from flask import render_template
-
 def errorResponse(errorMsg):
     return render_template('error.html',errorMsg=errorMsg)

utils/getPublicData.py

@@ -79,7 +79,7 @@ def getAllArticleData():
 
 def getAllHotWords():
     data = []
-    df = pd.read_csv('./model/cipingTotal.csv',encoding='utf8')
+    df = pd.read_csv('./utils/cipingTotal.csv',encoding='utf8')
     for i in df.values:
         try:
             data.append([

utils/stopWords.txt

@@ -719,6 +719,8 @@ sup
 哇
 哈
 哈哈
+哈哈哈
+哈哈哈哈
 哉
 哎
 哎呀
@@ -742,7 +744,13 @@ sup
 哼唷
 唉
 唯有
+特别
+超级
+越来
+越来越
 啊
+啊啊
+啊啊啊
 啊呀
 啊哈
 啊哟

views/user/user.py

@@ -1,48 +1,69 @@
 import time
-from flask import Blueprint, redirect, render_template, request,Flask, session
+import hashlib
+from flask import Blueprint, redirect, render_template, request, Flask, session
 
 from utils.query import query
 from utils.errorResponse import errorResponse
 
+ub = Blueprint('user',
+               __name__,
+               url_prefix='/user',
+               template_folder='templates')
 
-ub = Blueprint('user',__name__,url_prefix='/user',template_folder='templates')
 
-@ub.route('/login',methods=['GET','POST'])
+@ub.route('/login', methods=['GET', 'POST'])
 def login():
     if request.method == 'GET':
         return render_template('login.html')
     else:
+
         def filter_fn(user):
-            return request.form['username'] in user and request.form['password'] in user
+            hash_with_salt = hashlib.sha256('XiaoXueQi2024'.encode('utf-8'))
+            hash_with_salt.update(request.form['password'].encode('utf-8'))
+            return request.form[
+                'username'] in user and hash_with_salt.hexdigest() in user
+
         users = query('select * from user', [], 'select')
-        login_success = list(filter(filter_fn,users))
+        login_success = list(filter(filter_fn, users))
-        if not len(login_success):return errorResponse('账号或密码错误')
+        if not len(login_success): return errorResponse('账号或密码错误')
 
         session['username'] = request.form['username']
         return redirect('/page/home')
 
-@ub.route('/register',methods=['GET','POST'])
+
+@ub.route('/register', methods=['GET', 'POST'])
 def register():
     if request.method == 'GET':
         return render_template('register.html')
     else:
-        if request.form['password'] != request.form['checkPassword']:return errorResponse('两次密码不符合')
+        if request.form['password'] != request.form['checkPassword']:
+            return errorResponse('两次密码不符合')
+
         def filter_fn(user):
             return request.form['username'] in user
 
-        users = query('select * from user',[],'select')
+        users = query('select * from user', [], 'select')
-        filter_list = list(filter(filter_fn,users))
+        filter_list = list(filter(filter_fn, users))
         if len(filter_list):
             return errorResponse('该用户名已被注册')
         else:
             time_tuple = time.localtime(time.time())
-            query('''
+            hash_with_salt = hashlib.sha256('XiaoXueQi2024'.encode('utf-8'))
+            hash_with_salt.update(request.form['password'].encode('utf-8'))
+            query(
+                '''
                 insert into user(username,password,createTime) values(%s,%s,%s)
-            ''',[request.form['username'],request.form['password'],str(time_tuple[0]) + '-' + str(time_tuple[1]) + '-' + str(time_tuple[2])])
+            ''', [
+                    request.form['username'],
+                    hash_with_salt.hexdigest(),
+                    str(time_tuple[0]) + '-' + str(time_tuple[1]) + '-' +
+                    str(time_tuple[2])
+                ])
 
         return redirect('/user/login')
 
+
 @ub.route('/logOut')
 def logOut():
-        session.clear()
+    session.clear()
-        return redirect('/user/login')
+    return redirect('/user/login')